mirror of
https://github.com/immich-app/immich.git
synced 2026-05-18 03:10:24 +03:00
feat: ocr (#18836)
* feat: add OCR functionality and related configurations * chore: update labeler configuration for machine learning files * feat(i18n): enhance OCR model descriptions and add orientation classification and unwarping features * chore: update Dockerfile to include ccache for improved build performance * feat(ocr): enhance OCR model configuration with orientation classification and unwarping options, update PaddleOCR integration, and improve response structure * refactor(ocr): remove OCR_CLEANUP job from enum and type definitions * refactor(ocr): remove obsolete OCR entity and migration files, and update asset job status and schema to accommodate new OCR table structure * refactor(ocr): update OCR schema and response structure to use individual coordinates instead of bounding box, and adjust related service and repository files * feat: enhance OCR configuration and functionality - Updated OCR settings to include minimum detection box score, minimum detection score, and minimum recognition score. - Refactored PaddleOCRecognizer to utilize new scoring parameters. - Introduced new database tables for asset OCR data and search functionality. - Modified related services and repositories to support the new OCR features. - Updated translations for improved clarity in settings UI. * sql changes * use rapidocr * change dto * update web * update lock * update api * store positions as normalized floats * match column order in db * update admin ui settings descriptions fix max resolution key set min threshold to 0.1 fix bind * apply config correctly, adjust defaults * unnecessary model type * unnecessary sources * fix(ocr): switch RapidOCR lang type from LangDet to LangRec * fix(ocr): expose lang_type (LangRec.CH) and font_path on OcrOptions for RapidOCR * fix(ocr): make OCR text search case- and accent-insensitive using ILIKE + unaccent * fix(ocr): add OCR search fields * fix: Add OCR database migration and update ML prediction logic. * trigrams are already case insensitive * add tests * format * update migrations * wrong uuid function * linting * maybe fix medium tests * formatting * fix weblate check * openapi * sql * minor fixes * maybe fix medium tests part 2 * passing medium tests * format web * readd sql * format dart * disabled in e2e * chore: translation ordering --------- Co-authored-by: mertalev <101130780+mertalev@users.noreply.github.com> Co-authored-by: Alex Tran <alex.tran1502@gmail.com>
This commit is contained in:
@@ -1,6 +1,6 @@
|
||||
enum SortOrder { asc, desc }
|
||||
|
||||
enum TextSearchType { context, filename, description }
|
||||
enum TextSearchType { context, filename, description, ocr }
|
||||
|
||||
enum AssetVisibilityEnum { timeline, hidden, archive, locked }
|
||||
|
||||
|
||||
@@ -43,6 +43,7 @@ class SearchApiRepository extends ApiRepository {
|
||||
originalFileName: filter.filename != null && filter.filename!.isNotEmpty ? filter.filename : null,
|
||||
country: filter.location.country,
|
||||
description: filter.description != null && filter.description!.isNotEmpty ? filter.description : null,
|
||||
ocr: filter.ocr != null && filter.ocr!.isNotEmpty ? filter.ocr : null,
|
||||
state: filter.location.state,
|
||||
city: filter.location.city,
|
||||
make: filter.camera.make,
|
||||
|
||||
@@ -176,6 +176,7 @@ class SearchFilter {
|
||||
String? context;
|
||||
String? filename;
|
||||
String? description;
|
||||
String? ocr;
|
||||
String? language;
|
||||
Set<PersonDto> people;
|
||||
SearchLocationFilter location;
|
||||
@@ -190,6 +191,7 @@ class SearchFilter {
|
||||
this.context,
|
||||
this.filename,
|
||||
this.description,
|
||||
this.ocr,
|
||||
this.language,
|
||||
required this.people,
|
||||
required this.location,
|
||||
@@ -203,6 +205,7 @@ class SearchFilter {
|
||||
return (context == null || (context != null && context!.isEmpty)) &&
|
||||
(filename == null || (filename!.isEmpty)) &&
|
||||
(description == null || (description!.isEmpty)) &&
|
||||
(ocr == null || (ocr!.isEmpty)) &&
|
||||
people.isEmpty &&
|
||||
location.country == null &&
|
||||
location.state == null &&
|
||||
@@ -222,6 +225,7 @@ class SearchFilter {
|
||||
String? filename,
|
||||
String? description,
|
||||
String? language,
|
||||
String? ocr,
|
||||
Set<PersonDto>? people,
|
||||
SearchLocationFilter? location,
|
||||
SearchCameraFilter? camera,
|
||||
@@ -234,6 +238,7 @@ class SearchFilter {
|
||||
filename: filename ?? this.filename,
|
||||
description: description ?? this.description,
|
||||
language: language ?? this.language,
|
||||
ocr: ocr ?? this.ocr,
|
||||
people: people ?? this.people,
|
||||
location: location ?? this.location,
|
||||
camera: camera ?? this.camera,
|
||||
@@ -245,7 +250,7 @@ class SearchFilter {
|
||||
|
||||
@override
|
||||
String toString() {
|
||||
return 'SearchFilter(context: $context, filename: $filename, description: $description, language: $language, people: $people, location: $location, camera: $camera, date: $date, display: $display, mediaType: $mediaType)';
|
||||
return 'SearchFilter(context: $context, filename: $filename, description: $description, language: $language, ocr: $ocr, people: $people, location: $location, camera: $camera, date: $date, display: $display, mediaType: $mediaType)';
|
||||
}
|
||||
|
||||
@override
|
||||
@@ -256,6 +261,7 @@ class SearchFilter {
|
||||
other.filename == filename &&
|
||||
other.description == description &&
|
||||
other.language == language &&
|
||||
other.ocr == ocr &&
|
||||
other.people == people &&
|
||||
other.location == location &&
|
||||
other.camera == camera &&
|
||||
@@ -270,6 +276,7 @@ class SearchFilter {
|
||||
filename.hashCode ^
|
||||
description.hashCode ^
|
||||
language.hashCode ^
|
||||
ocr.hashCode ^
|
||||
people.hashCode ^
|
||||
location.hashCode ^
|
||||
camera.hashCode ^
|
||||
|
||||
@@ -389,15 +389,18 @@ class SearchPage extends HookConsumerWidget {
|
||||
handleTextSubmitted(String value) {
|
||||
switch (textSearchType.value) {
|
||||
case TextSearchType.context:
|
||||
filter.value = filter.value.copyWith(filename: '', context: value, description: '');
|
||||
filter.value = filter.value.copyWith(filename: '', context: value, description: '', ocr: '');
|
||||
|
||||
break;
|
||||
case TextSearchType.filename:
|
||||
filter.value = filter.value.copyWith(filename: value, context: '', description: '');
|
||||
filter.value = filter.value.copyWith(filename: value, context: '', description: '', ocr: '');
|
||||
|
||||
break;
|
||||
case TextSearchType.description:
|
||||
filter.value = filter.value.copyWith(filename: '', context: '', description: value);
|
||||
filter.value = filter.value.copyWith(filename: '', context: '', description: value, ocr: '');
|
||||
break;
|
||||
case TextSearchType.ocr:
|
||||
filter.value = filter.value.copyWith(filename: '', context: '', description: '', ocr: value);
|
||||
break;
|
||||
}
|
||||
|
||||
@@ -408,6 +411,7 @@ class SearchPage extends HookConsumerWidget {
|
||||
TextSearchType.context => Icons.image_search_rounded,
|
||||
TextSearchType.filename => Icons.abc_rounded,
|
||||
TextSearchType.description => Icons.text_snippet_outlined,
|
||||
TextSearchType.ocr => Icons.document_scanner_outlined,
|
||||
};
|
||||
|
||||
return Scaffold(
|
||||
@@ -493,6 +497,24 @@ class SearchPage extends HookConsumerWidget {
|
||||
searchHintText.value = 'search_by_description_example'.tr();
|
||||
},
|
||||
),
|
||||
MenuItemButton(
|
||||
child: ListTile(
|
||||
leading: const Icon(Icons.document_scanner_outlined),
|
||||
title: Text(
|
||||
'search_filter_ocr'.tr(),
|
||||
style: context.textTheme.bodyLarge?.copyWith(
|
||||
fontWeight: FontWeight.w500,
|
||||
color: textSearchType.value == TextSearchType.ocr ? context.colorScheme.primary : null,
|
||||
),
|
||||
),
|
||||
selectedColor: context.colorScheme.primary,
|
||||
selected: textSearchType.value == TextSearchType.ocr,
|
||||
),
|
||||
onPressed: () {
|
||||
textSearchType.value = TextSearchType.ocr;
|
||||
searchHintText.value = 'search_by_ocr_example'.tr();
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
),
|
||||
|
||||
@@ -395,15 +395,18 @@ class DriftSearchPage extends HookConsumerWidget {
|
||||
handleTextSubmitted(String value) {
|
||||
switch (textSearchType.value) {
|
||||
case TextSearchType.context:
|
||||
filter.value = filter.value.copyWith(filename: '', context: value, description: '');
|
||||
filter.value = filter.value.copyWith(filename: '', context: value, description: '', ocr: '');
|
||||
|
||||
break;
|
||||
case TextSearchType.filename:
|
||||
filter.value = filter.value.copyWith(filename: value, context: '', description: '');
|
||||
filter.value = filter.value.copyWith(filename: value, context: '', description: '', ocr: '');
|
||||
|
||||
break;
|
||||
case TextSearchType.description:
|
||||
filter.value = filter.value.copyWith(filename: '', context: '', description: value);
|
||||
filter.value = filter.value.copyWith(filename: '', context: '', description: value, ocr: '');
|
||||
break;
|
||||
case TextSearchType.ocr:
|
||||
filter.value = filter.value.copyWith(filename: '', context: '', description: '', ocr: value);
|
||||
break;
|
||||
}
|
||||
|
||||
@@ -414,6 +417,7 @@ class DriftSearchPage extends HookConsumerWidget {
|
||||
TextSearchType.context => Icons.image_search_rounded,
|
||||
TextSearchType.filename => Icons.abc_rounded,
|
||||
TextSearchType.description => Icons.text_snippet_outlined,
|
||||
TextSearchType.ocr => Icons.document_scanner_outlined,
|
||||
};
|
||||
|
||||
return Scaffold(
|
||||
@@ -499,6 +503,24 @@ class DriftSearchPage extends HookConsumerWidget {
|
||||
searchHintText.value = 'search_by_description_example'.t(context: context);
|
||||
},
|
||||
),
|
||||
MenuItemButton(
|
||||
child: ListTile(
|
||||
leading: const Icon(Icons.document_scanner_outlined),
|
||||
title: Text(
|
||||
'search_by_ocr'.t(context: context),
|
||||
style: context.textTheme.bodyLarge?.copyWith(
|
||||
fontWeight: FontWeight.w500,
|
||||
color: textSearchType.value == TextSearchType.ocr ? context.colorScheme.primary : null,
|
||||
),
|
||||
),
|
||||
selectedColor: context.colorScheme.primary,
|
||||
selected: textSearchType.value == TextSearchType.ocr,
|
||||
),
|
||||
onPressed: () {
|
||||
textSearchType.value = TextSearchType.ocr;
|
||||
searchHintText.value = 'search_by_ocr_example'.t(context: context);
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
),
|
||||
|
||||
Reference in New Issue
Block a user